Helena Gómez-Adorno
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Helena Gómez-Adorno has a total of 99 co-authors. Here are the top co-authors by number of shared publications:
- Gemma Bel-Enguix
Instituto de Ingeniería, Universidad Nacional Autónoma de México, Avenida Universidad 3000, Mexico City 04510, Mexico
10 shared publications David Pinto
Benemerita Universidad Autónoma de Puebla (BUAP)
8 shared publications- Gerardo Sierra
Universidad Nacional Autónoma de México
7 shared publications - Grigori Sidorov
Instituto Politécnico Nacional
6 shared publications Grigori Sidorov
Centro de Investigacion en Computacion (CIC), Instituto Politecnico Nacional, Mexico
5 shared publicationsDarnes Vilariño
Facultad de Ciencias de la Computación, Benemérita Universidad Autónoma de Puebla, México
4 shared publications
Latest Publications
- Open Access
- 9 October 2026
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 32
An intelligent RAG-based framework for evidence-grounded verification of LLM-generated CVE–ATT&CK mappings
- 9 October 2026
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 32
Open AccessAn intelligent RAG-based framework for evidence-grounded verification of LLM-generated CVE–ATT&CK mappings
- 29 September 2026
- Published by Springer Nature
- p. 252-268
CIPA: A Multi-domain Statistical Framework for Characterizing Imbalanced Datasets and Computing a Difficulty Score
- 29 September 2026
- Published by Springer Nature
- p. 252-268
CIPA: A Multi-domain Statistical Framework for Characterizing Imbalanced Datasets and Computing a Difficulty Score
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (6) , 539-549
Detecting Obstetric Violence Tweets from Mexico: Annotation Guidelines and Classification with LLMs
This paper presents the construction and analysis of a manually annotated corpus of tweets related to Obstetric Violence (OV) shared on Twitter (now X). The study aims to identify different types of violence experienced by women during the perinatal period, as well as activism efforts that seek to raise awareness about OV. The methodology includes data collection through keyword filtering, manual annotation guided by typologies of OV, and a descriptive analysis using BERTopic to identify themes in the data. The tweets were classified into categories such as OV, Non-OV, and Activism, and further annotated based on narrator type and type of OV violence. The study also evaluates the performance of large language models (LLMs) including ChatGPT, Copilot, and Metas LLaMA for zero-shot classification of tweets, highlighting their limitations in accurately identifying nuanced cases of OV. The research contributes a labeled dataset, a detailed annotation guide, and insights into the challenges of detecting OV in social media texts. It underscores the importance of addressing the invisibility and normalization of OV in both healthcare and NLP research.
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (6) , 539-549
Detecting Obstetric Violence Tweets from Mexico: Annotation Guidelines and Classification with LLMs
This paper presents the construction and analysis of a manually annotated corpus of tweets related to Obstetric Violence (OV) shared on Twitter (now X). The study aims to identify different types of violence experienced by women during the perinatal period, as well as activism efforts that seek to raise awareness about OV. The methodology includes data collection through keyword filtering, manual annotation guided by typologies of OV, and a descriptive analysis using BERTopic to identify themes in the data. The tweets were classified into categories such as OV, Non-OV, and Activism, and further annotated based on narrator type and type of OV violence. The study also evaluates the performance of large language models (LLMs) including ChatGPT, Copilot, and Metas LLaMA for zero-shot classification of tweets, highlighting their limitations in accurately identifying nuanced cases of OV. The research contributes a labeled dataset, a detailed annotation guide, and insights into the challenges of detecting OV in social media texts. It underscores the importance of addressing the invisibility and normalization of OV in both healthcare and NLP research.
- Open Access
- 15 April 2026
- Published by Elsevier in Data in Brief
- Vol. 66, 112765
Dataset of manually curated peptides against arthropod-borne viruses
- 15 April 2026
- Published by Elsevier in Data in Brief
- Vol. 66, 112765
Open AccessDataset of manually curated peptides against arthropod-borne viruses
- 31 October 2025
- Published by Springer Nature
- p. 257-273
Automatic Classification of BI-RADS in Spanish Radiology Reports Using Transformers and Traditional Machine Learning Approaches
- 31 October 2025
- Published by Springer Nature
- p. 257-273
Automatic Classification of BI-RADS in Spanish Radiology Reports Using Transformers and Traditional Machine Learning Approaches
- 24 October 2025
- Published by Springer Nature
- p. 268-283
Automatic Synthetic Data Selection for Highly Imbalanced Multi-class and Multi-label Obstetric Violence Classification
- 24 October 2025
- Published by Springer Nature
- p. 268-283
Automatic Synthetic Data Selection for Highly Imbalanced Multi-class and Multi-label Obstetric Violence Classification
- Open Access
- 26 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 197 (Pt A) , 110964
Manual annotation of Robson criteria and obstetric entities: Inter-annotator agreement and initial NER models implementation
- 26 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 197 (Pt A) , 110964
Open AccessManual annotation of Robson criteria and obstetric entities: Inter-annotator agreement and initial NER models implementation
- Open Access
- 7 June 2025
- Published by Elsevier in Data in Brief
- Vol. 61, 111761
Mammography reporting dataset with BI-RADS system for natural language processing applications: Addressing public data gaps in Spanish
- 7 June 2025
- Published by Elsevier in Data in Brief
- Vol. 61, 111761
Open AccessMammography reporting dataset with BI-RADS system for natural language processing applications: Addressing public data gaps in Spanish
- Open Access
- 18 March 2025
- Published by Editorial Académica Dragón Azteca in International Journal of Combinatorial Optimization Problems and Informatics
- Vol. 16 (1) , 177-189
A similarity Based Algorithm for Predicting Academic Success in First-year Undergraduates
According to the European Commission, “Early school leaving is linked to unemployment, social exclusion, poverty, and poor health” (European Commission, 2024). Due to the importance of reducing school drop-out rates, several authors have analyzed this phenomenon. Before the boom of Artificial Intelligence, instead of using or implementing programming methods, researchers applied written formulas and rudimentary graphical visualizations to predict academic completion and the main factors behind it; besides, the development of Machine Learning (ML) algorithms has enhanced the precision and performance of an ample variety of investigations including the educational field. In this paper, we use a dataset of undergraduate-level students at the Universidad Nacional Autónoma de Mexico (UNAM) to predict timely academic completion. We use seven common ML algorithms and propose a novel algorithm based on students' similarities according to the most relevant features in common. This algorithm shows a higher precision than some traditional categorical ML algorithms. This innovative way to predict academic success can support educators, pedagogues, and policymakers make better decisions at UNAM.
- 18 March 2025
- Published by Editorial Académica Dragón Azteca in International Journal of Combinatorial Optimization Problems and Informatics
- Vol. 16 (1) , 177-189
Open AccessA similarity Based Algorithm for Predicting Academic Success in First-year Undergraduates
According to the European Commission, “Early school leaving is linked to unemployment, social exclusion, poverty, and poor health” (European Commission, 2024). Due to the importance of reducing school drop-out rates, several authors have analyzed this phenomenon. Before the boom of Artificial Intelligence, instead of using or implementing programming methods, researchers applied written formulas and rudimentary graphical visualizations to predict academic completion and the main factors behind it; besides, the development of Machine Learning (ML) algorithms has enhanced the precision and performance of an ample variety of investigations including the educational field. In this paper, we use a dataset of undergraduate-level students at the Universidad Nacional Autónoma de Mexico (UNAM) to predict timely academic completion. We use seven common ML algorithms and propose a novel algorithm based on students' similarities according to the most relevant features in common. This algorithm shows a higher precision than some traditional categorical ML algorithms. This innovative way to predict academic success can support educators, pedagogues, and policymakers make better decisions at UNAM.
- Open Access
- 6 November 2024
- Published by Springer Nature in Research Square
MIND-HOPE: Multilingual Identification of Nuanced Dimensions of HOPE
Hope plays a crucial role in human psychology, yet research on its expression and detection across languages is limited. This study addresses this gap by developing the first multiclass hope speech detection datasets for Spanish and German. The research includes a comprehensive review of existing datasets and techniques and employs various learning approaches—traditional machine learning, deep learning, and transformer-based models—to evaluate their effectiveness. The new datasets significantly advance hope speech detection by incorporating diverse linguistic contexts. Comparative analyses reveal that transformer models, such as xlm-roberta-base for Spanish and uklfr/gottbert-base for German, achieve superior performance with F1 scores of 0.6801 and 0.6977, respectively, in multiclass detection tasks compared to the rest of the models. Multilingual transformers are also promising in cross-lingual applications but require further refinement. This study sets the groundwork for future advancements by enhancing dataset diversity and model performance, with future research focusing on refining multilingual models and expanding to various languages.
- 6 November 2024
- Published by Springer Nature in Research Square
Open AccessMIND-HOPE: Multilingual Identification of Nuanced Dimensions of HOPE
Hope plays a crucial role in human psychology, yet research on its expression and detection across languages is limited. This study addresses this gap by developing the first multiclass hope speech detection datasets for Spanish and German. The research includes a comprehensive review of existing datasets and techniques and employs various learning approaches—traditional machine learning, deep learning, and transformer-based models—to evaluate their effectiveness. The new datasets significantly advance hope speech detection by incorporating diverse linguistic contexts. Comparative analyses reveal that transformer models, such as xlm-roberta-base for Spanish and uklfr/gottbert-base for German, achieve superior performance with F1 scores of 0.6801 and 0.6977, respectively, in multiclass detection tasks compared to the rest of the models. Multilingual transformers are also promising in cross-lingual applications but require further refinement. This study sets the groundwork for future advancements by enhancing dataset diversity and model performance, with future research focusing on refining multilingual models and expanding to various languages.